Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/morodomi/dev-crew/cycle-retrospectivenpx skills add morodomi/dev-crew --skill cycle-retrospectivegit clone --depth 1 https://github.com/morodomi/dev-crewWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/morodomi/dev-crew/cycle-retrospective)<a href="https://agentmods.dev/skills/morodomi/dev-crew/cycle-retrospective"><img src="https://agentmods.dev/badge/skills/morodomi/dev-crew/cycle-retrospective.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00097 | $0.00868 |
| Opus 5 | $0.00048 | $0.00434 |
| Sonnet 5 | $0.00019 | $0.00174 |
| Haiku 4.5 | $0.00010 | $0.00087 |
Grade A, and why
cycle-retrospective scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
cycle-retrospective
Workflow
Hard Gate
- Cycle doc 存在: 不在 → BLOCK: 「先に spec/orchestrate を実行してください」
- Phase 制約 (Codex P2-1 対応、mid-cycle 実行で A2b inline 呼び出しの順序が永続破壊されるのを防ぐ): phase が
REVIEW/COMMIT/DONEのいずれかのみ許可。INIT/KICKOFF/RED/GREEN/REFACTOR→ BLOCK: 「cycle-retrospective は REVIEW phase 以降で実行してください (現 phase: $phase)」
Idempotency Check
- frontmatter
retro_statusがnone以外 (captured / resolved / フィールド不在) → skip + 「既に処理済み (retro_status: $value)」を出力して exit 0 retro_status: noneの場合のみ抽出フェーズへ進む
Extraction (LLM)
- Cycle doc 全体を読む (plan / phase summaries / review verdicts / test failures / retry log / DISCOVERED)
- Failure → Final fix → Insight ペアを抽出 (詳細手順: reference.md)
- 想起漏れ設問を評価: 今回の手戻りは過去のどの cycle doc を最初に読んでいれば防げたか（該当なし可、reference.md の
### 想起漏れスキーマで記録） - 抽出 0 件 (no reusable lesson) — 抽出は成功したが再利用可能な知見が見つからないケース (Codex P2-2 対応): 通常 exit path、Retrospective に
No reusable lesson this cycleを記録して retro_status: resolved に遷移 (user intervention 不要、AskUserQuestion も実行しない) - 抽出エラー (LLM error / parse error) — LLM 実行自体が失敗したケース: retry N=2 → 全失敗時は AskUserQuestion で override (proceed / abort)。no-lesson path と混同しない
Output (Cycle doc 更新)
state-ownership.md の cycle-retrospective 行に従う:
- Body:
## Retrospectiveを Cycle doc EOF (## Next Stepsの後) に append (APPEND-ONLY 遵守、middle-insert 禁止、既存内容は一切変更しない) - 想起漏れ記録: 全正常終了経路（通常テンプレート / no-lesson / override-proceed）で
### 想起漏れを記録する。abort（ファイル非変更）のみ対象外 - frontmatter:
retro_status(none → captured / none → resolved) とupdatedのみ更新captured: 有効な insight を追記した場合resolved: no-lesson / override-proceed (Extraction skipped by overrideまたはExtraction failed after N retries) の場合
- abort 選択時: Cycle doc は変更せず、stderr に「Retrospective aborted by user. orchestrate should BLOCK commit.」を出力して exit 1
Reference
詳細: reference.md
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 43 lines · 97 tokens per session scan A c2aba52e4f76
cycle-retrospective is a skill published in the GitHub repository morodomi/dev-crew (1 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 868 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-tdd
Build features with tests-before-code rigor — use for new features needing test coverage.
tdd
Guides test-driven development — decomposes a feature or bug fix into testable behaviors, then runs Red-Green-Refactor cycles with a failing test before every implementation. Auto-detects specs from docs/specs/ or docs/jira/, creates a feature branch (optional worktree), commits per cycle, and pushes. Recommends…
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
test-first
Drive one feature through a strict TDD Red-Green-Refactor cycle with checklists for each phase. Use when implementing new functionality test-first, or when the user runs /test-first.
plan-create
Create structured implementation plans for autonomous TDD development. Use for new features, multi-file changes, or anything requiring multiple steps or tests. Triggers on aspirational openers ("let's build", "let's start building", "I want to make", "I want an app that", "help me build"), capability lists ("users…